Tesla K40m vs GeForce GT 640M
Aggregate performance score
We've compared GeForce GT 640M with Tesla K40m, including specs and performance data.
K40m outperforms 640M by a whopping 255% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 923 | 578 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 0.06 |
| Power efficiency | 5.10 | 2.36 |
| Architecture | Kepler (2012−2018) | Kepler (2012−2018) |
| GPU code name | GK107 | GK110B |
| Market segment | Laptop | Workstation |
| Release date | 22 March 2012 (14 years ago) | 22 November 2013 (12 years ago) |
| Launch price (MSRP) | no data | $7,699 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 384 | 2880 |
| Core clock speed | Up to 625 MHz | 745 MHz |
| Boost clock speed | 645 MHz | 876 MHz |
| Number of transistors | 1,270 million | 7,080 million |
| Manufacturing process technology | 28 nm | 28 nm |
| Power consumption (TDP) | 32 Watt | 245 Watt |
| Texture fill rate | 20.00 | 210.2 |
| Floating-point processing power | 0.48 TFLOPS | 5.046 TFLOPS |
| ROPs | 16 | 48 |
| TMUs | 32 | 240 |
| L1 Cache | 32 KB | 240 KB |
| L2 Cache | 256 KB | 1536 KB |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Laptop size | medium sized | no data |
| Bus support | PCI Express 2.0, PCI Express 3.0 | no data |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Length | no data | 267 mm |
| Width | no data | 2-slot |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | DDR3\GDDR5 | GDDR5 |
| Maximum RAM amount | 2 GB | 12 GB |
| Memory bus width | 128bit | 384 Bit |
| Memory clock speed | 900 MHz | 1502 MHz |
| Memory bandwidth | Up to 64.0 GB/s | 288.4 GB/s |
| Shared memory | - | - |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | No outputs | No outputs |
| HDMI | + | - |
| HDCP | + | - |
| Maximum VGA resolution | Up to 2048x1536 | no data |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| 3D Blu-Ray | + | - |
| Optimus | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 API | 12 (11_1) |
| Shader Model | 5.1 | 5.1 |
| OpenGL | 4.5 | 4.6 |
| OpenCL | 1.1 | 1.2 |
| Vulkan | 1.1.126 | 1.1.126 |
| CUDA | + | 3.5 |
Synthetic benchmarks
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
GeekBench 5 CUDA
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses CUDA API by NVIDIA.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| 900p | 24
−254%
| 85−90
+254%
|
| Full HD | 22
−241%
| 75−80
+241%
|
| 1200p | 19
−242%
| 65−70
+242%
|
Cost per frame, $
| 1080p | no data | 102.65 |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 4−5
−250%
|
14−16
+250%
|
| Cyberpunk 2077 | 4−5
−250%
|
14−16
+250%
|
| Resident Evil 4 Remake | 2−3
−250%
|
7−8
+250%
|
Full HD
Medium
| Battlefield 5 | 6−7
−250%
|
21−24
+250%
|
| Counter-Strike 2 | 4−5
−250%
|
14−16
+250%
|
| Cyberpunk 2077 | 4−5
−250%
|
14−16
+250%
|
| Far Cry 5 | 5−6
−220%
|
16−18
+220%
|
| Fortnite | 10−11
−250%
|
35−40
+250%
|
| Forza Horizon 4 | 10−12
−218%
|
35−40
+218%
|
| Forza Horizon 5 | 4−5
−250%
|
14−16
+250%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−233%
|
40−45
+233%
|
| Valorant | 40−45
−250%
|
140−150
+250%
|
Full HD
High
| Battlefield 5 | 6−7
−250%
|
21−24
+250%
|
| Counter-Strike 2 | 4−5
−250%
|
14−16
+250%
|
| Counter-Strike: Global Offensive | 49
−247%
|
170−180
+247%
|
| Cyberpunk 2077 | 4−5
−250%
|
14−16
+250%
|
| Dota 2 | 25
−240%
|
85−90
+240%
|
| Far Cry 5 | 5−6
−220%
|
16−18
+220%
|
| Fortnite | 10−11
−250%
|
35−40
+250%
|
| Forza Horizon 4 | 10−12
−218%
|
35−40
+218%
|
| Forza Horizon 5 | 4−5
−250%
|
14−16
+250%
|
| Grand Theft Auto V | 8
−238%
|
27−30
+238%
|
| Metro Exodus | 3−4
−233%
|
10−11
+233%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−233%
|
40−45
+233%
|
| The Witcher 3: Wild Hunt | 8−9
−238%
|
27−30
+238%
|
| Valorant | 40−45
−250%
|
140−150
+250%
|
Full HD
Ultra
| Battlefield 5 | 6−7
−250%
|
21−24
+250%
|
| Cyberpunk 2077 | 4−5
−250%
|
14−16
+250%
|
| Dota 2 | 24
−254%
|
85−90
+254%
|
| Far Cry 5 | 5−6
−220%
|
16−18
+220%
|
| Forza Horizon 4 | 10−12
−218%
|
35−40
+218%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−233%
|
40−45
+233%
|
| The Witcher 3: Wild Hunt | 8−9
−238%
|
27−30
+238%
|
| Valorant | 40−45
−250%
|
140−150
+250%
|
Full HD
Epic
| Fortnite | 10−11
−250%
|
35−40
+250%
|
1440p
High
| Counter-Strike 2 | 5−6
−220%
|
16−18
+220%
|
| Counter-Strike: Global Offensive | 14−16
−233%
|
50−55
+233%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 21−24
−233%
|
70−75
+233%
|
| Valorant | 16−18
−244%
|
55−60
+244%
|
1440p
Ultra
| Cyberpunk 2077 | 1−2
−200%
|
3−4
+200%
|
| Far Cry 5 | 3−4
−233%
|
10−11
+233%
|
| Forza Horizon 4 | 5−6
−220%
|
16−18
+220%
|
| The Witcher 3: Wild Hunt | 3−4
−233%
|
10−11
+233%
|
1440p
Epic
| Fortnite | 4−5
−250%
|
14−16
+250%
|
4K
High
| Grand Theft Auto V | 14−16
−221%
|
45−50
+221%
|
| Valorant | 10−11
−250%
|
35−40
+250%
|
4K
Ultra
| Cyberpunk 2077 | 0−1 | 0−1 |
| Dota 2 | 5−6
−220%
|
16−18
+220%
|
| Far Cry 5 | 1−2
−200%
|
3−4
+200%
|
| Forza Horizon 4 | 1−2
−200%
|
3−4
+200%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 3−4
−233%
|
10−11
+233%
|
4K
Epic
| Fortnite | 3−4
−233%
|
10−11
+233%
|
This is how GT 640M and Tesla K40m compete in popular games:
- Tesla K40m is 254% faster in 900p
- Tesla K40m is 241% faster in 1080p
- Tesla K40m is 242% faster in 1200p
Pros & cons summary
| Performance score | 2.12 | 7.52 |
| Recency | 22 March 2012 | 22 November 2013 |
| Maximum RAM amount | 2 GB | 12 GB |
| Power consumption (TDP) | 32 Watt | 245 Watt |
GT 640M has 666% lower power consumption.
Tesla K40m, on the other hand, has a 255% higher aggregate performance score, an age advantage of 1 year, and a 500% higher maximum VRAM amount.
The Tesla K40m is our recommended choice as it beats the GeForce GT 640M in performance tests.
Be aware that GeForce GT 640M is a notebook graphics card while Tesla K40m is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
